Papers › What Helps Transformers Recognize Conversational Structure? Importance of Context,...

What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition

5 Jul 2021arXiv:2107.02294archive 2025-07-28

Piotr Żelasko, Raghavendra Pappagari, Najim Dehak

Dialog acts can be interpreted as the atomic units of a conversation, more fine-grained than utterances, characterized by a specific communicative function. The ability to structure a conversational transcript as a sequence of dialog acts -- dialog act recognition, including the segmentation -- is critical for understanding dialog. We apply two pre-trained transformer models, XLNet and Longformer, to this task in English and achieve strong results on Switchboard Dialog Act and Meeting Recorder Dialog Act corpora with dialog act segmentation error rates (DSER) of 8.4% and 14.2%. To understand the key factors affecting dialog act recognition, we perform a comparative analysis of models trained under different conditions. We find that the inclusion of a broader conversational context helps disambiguate many dialog act classes, especially those infrequent in the training data. The presence of punctuation in the transcripts has a massive effect on the models' performance, and a detailed analysis reveals specific segmentation patterns observed in its absence. Finally, we find that the label set specificity does not affect dialog act segmentation performance. These findings have significant practical implications for spoken language understanding applications that depend heavily on a good-quality segmentation being available.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pzelasko/daseg officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

SegmentationSpecificitySpoken Language Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAdamWAttentionAttention DropoutBPEDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayLongformerMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxWeight DecayWordPieceXLNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections